Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
47.31MultiHop F1
36
Jun 23, 2026
39.8S-Doc QA Accuracy
36
Jun 4, 2026
54Agent Turns
36
Jun 1, 2026
64.1ARC-C Score
36
May 28, 2026
85.4Accuracy (ARC-E)
36
May 28, 2026
69.8Accuracy (One Intent)
36
May 26, 2026
45.27Overall Average RAG F1
36
May 12, 2026
72.6F1 Score
36
Apr 14, 2026
100ASR
36
Apr 10, 2026
1ASR Score
36
Apr 10, 2026
82.4Accuracy
36
Mar 24, 2026
90.6NQ Recall (%)
36
Mar 18, 2026
92.3Recall (%)
36
Mar 18, 2026
79.38Zero-shot Accuracy
36
Feb 27, 2026
48.46Zero-shot Accuracy
36
Feb 27, 2026
35.2Zero-shot Accuracy
36
Feb 27, 2026
0.741Pearson's r
36
Feb 26, 2026
81.77Accuracy
36
Mar 4, 2026
79.1Accuracy
36
Apr 10, 2026
78.7Accuracy
36
Apr 27, 2026
69.5F1 Score
36
Feb 26, 2026
33.61F1
36
Feb 26, 2026
71.4F1 Score
36
Feb 26, 2026
92.9Accuracy
36
Jul 3, 2026
46.39Accuracy
36
May 11, 2026